def test_io_api(tmp_path):
num_instances = 20
image_x = utils.generate_data(num_instances=num_instances, shape=(28, 28))
text_x = utils.generate_text_data(num_instances=num_instances)
image_x = image_x[:num_instances]
structured_data_x = (pd.read_csv(utils.TRAIN_CSV_PATH).to_numpy().astype(
np.unicode)[:num_instances])
classification_y = utils.generate_one_hot_labels(
num_instances=num_instances, num_classes=3)
regression_y = utils.generate_data(num_instances=num_instances,
shape=(1, ))
# Build model and train.
automodel = ak.AutoModel(
inputs=[ak.ImageInput(),
ak.TextInput(),
ak.StructuredDataInput()],
outputs=[
ak.RegressionHead(metrics=["mae"]),
ak.ClassificationHead(loss="categorical_crossentropy",
metrics=["accuracy"]),
],
directory=tmp_path,
max_trials=2,
tuner=ak.RandomSearch,
seed=utils.SEED,
)
automodel.fit(
[image_x, text_x, structured_data_x],
[regression_y, classification_y],
epochs=1,
validation_split=0.2,
batch_size=4,
)
def test_text_regressor(tmp_path):
train_x = utils.generate_text_data(num_instances=300)
test_x = train_x
train_y = utils.generate_data(num_instances=300, shape=(1,))
test_y = train_y
clf = ak.TextRegressor(directory=tmp_path, max_trials=2, seed=utils.SEED)
clf.fit(train_x, train_y, epochs=1, validation_data=(test_x, test_y))
clf.export_model()
assert clf.predict(test_x).shape == (len(test_x), 1)
def test_text_and_structured_data(tmp_path):
# Prepare the data.
num_instances = 80
x_text = utils.generate_text_data(num_instances)
x_structured_data = pd.read_csv(utils.TRAIN_CSV_PATH)
x_structured_data = x_structured_data[:num_instances]
y_classification = utils.generate_one_hot_labels(
num_instances=num_instances, num_classes=3
)
y_regression = utils.generate_data(num_instances=num_instances, shape=(1,))
# Build model and train.
structured_data_input = ak.StructuredDataInput()
structured_data_output = ak.CategoricalToNumerical()(structured_data_input)
structured_data_output = ak.DenseBlock()(structured_data_output)
text_input = ak.TextInput()
outputs1 = ak.TextToIntSequence()(text_input)
outputs1 = ak.Embedding()(outputs1)
outputs1 = ak.ConvBlock(separable=True)(outputs1)
outputs1 = ak.SpatialReduction()(outputs1)
outputs2 = ak.TextToNgramVector()(text_input)
outputs2 = ak.DenseBlock()(outputs2)
text_output = ak.Merge()((outputs1, outputs2))
merged_outputs = ak.Merge()((structured_data_output, text_output))
regression_outputs = ak.RegressionHead()(merged_outputs)
classification_outputs = ak.ClassificationHead()(merged_outputs)
automodel = ak.AutoModel(
inputs=[text_input, structured_data_input],
directory=tmp_path,
outputs=[regression_outputs, classification_outputs],
max_trials=2,
tuner=ak.Hyperband,
seed=utils.SEED,
)
automodel.fit(
(x_text, x_structured_data),
(y_regression, y_classification),
validation_split=0.2,
epochs=1,
)
def test_text_classifier(tmp_path):
train_x = utils.generate_text_data(num_instances=320)
train_y = np.random.randint(0, 2, 320)
test_x = train_x
test_y = train_y
clf = ak.TextClassifier(
directory=tmp_path,
max_trials=2,
seed=utils.SEED,
metrics=["accuracy"],
objective="accuracy",
)
clf.fit(
train_x, train_y, epochs=2, validation_data=(test_x, test_y), batch_size=6
)
clf.export_model()
assert clf.predict(test_x).shape == (len(test_x), 1)
assert clf.tuner._get_best_trial_epochs() <= 2
def test_preprocessing_adapt_with_text_vec():
class MockLayer(preprocessing.TextVectorization):
def adapt(self, *args, **kwargs):
super().adapt(*args, **kwargs)
self.is_called = True
x_train = utils.generate_text_data()
y_train = np.random.randint(0, 2, (100, ))
dataset = tf.data.Dataset.from_tensor_slices((x_train, y_train)).batch(32)
layer1 = MockLayer(max_tokens=5000,
output_mode="int",
output_sequence_length=40)
model = tf.keras.models.Sequential()
model.add(tf.keras.Input(shape=(1, ), dtype=tf.string))
model.add(layer1)
model.add(tf.keras.layers.Embedding(50001, 10))
model.add(tf.keras.layers.Dense(1))
tuner_module.AutoTuner.adapt(model, dataset)
assert layer1.is_called